Computer Science, Electrical Engineering

SMD081 Artificial Neural Networks 6.0 ECTS credits

DENNA SIDA FINNS OCKSÅ PÅ SVENSKA

General information about studying at Luleå University
TIMEPERIOD:

LANGUAGE: English/Swedish

EXAMINER
Glenn Jennings Univ lekt

PREREQUISITES


COURSE AIM
The course is designed to give both a theoretical and practical understanding of learning systems, with emphasis on artificial neural networks.

CONTENTS
Background and overview of learning systems such as artificial neural networks, genetic algorithms, and fuzzy logic. The learning process and self-organizing systems. Classical learning systems such as correlation matrix memory, the perceptron, and the least-mean-square algorithm. Feedforward networks such as multilayer perceptrons and localized learning systems. Feedback networks and other dynamic networks, e.g., Hopfield networks. Temporal processing. Multi modular learning systems. Ways to implement learning systems in hardware. Applications of learning systems in areas such as signal processing, communication, control, robotics, and image processing.

TEACHING
Consists of lectures and laboratory work.

EXAMINATION
Evaluation is by a final examination, completed labwork and project report. The final grade is based on the final examination and on the student's participation in the project.
COURSE GRADE SCALE:

ITEMS AND CREDITS 
Laboratory work                                             	1.5 ECTS
Written exam                                                	4.5 ECTS

COURSE LITERATURE
Haykin, S., Neural Networks, a Comprehensive Foundation, New York: IEEE Computer Society Press, 1994, ISBN 0-02-352761-7. Scientific articles.

REMARKS
The course will not be given in the academic year 96/97.
Last modified 97-03-05
Further information: Glenn Jennings
Back to departement menu